ATI's X1000 Series: Extended Performance Testing
by Derek Wilson on October 7, 2005 10:15 AM EST- Posted in
- GPUs
Introduction
With our recent architecture and feature set coverage over the ATI Radeon X1000 series launch, we were a little bit light on the performance numbers. Rather than fill out some of the tests and update the article, we decided to take a little more time and do it up right. We have heard the call for more game tests, and today, we bring them on in spades. Our expanded tests include the games mentioned in our earlier coverage, the much requested Battlefield 2, and we illustrate the stellar way in which the new X1000 series handles enabling 4xAA on the games that we tested.
While scaling-with-aa on the new X1000 series is very good, will it be good enough to make up for the price difference with competitive NVIDIA hardware? Certainly, the feature set is of value with ATI offering the added benefit of MSAA on MRT and floating point surfaces, high quality AF, SM3.0, and Avivo. But performance is absolutely critical on current and near term games. Currently, many HDR methods avoid floating point output and MRTs in order to maintain compatibility with AA on current hardware. Until game developers shift to full floating point framebuffers or make heavy use of multiple render targets, ATI's added AA support won't make much difference to gamers. High quality anisotropic filtering is definitely something that we have begged of NVIDIA and ATI for a long time and we are glad to see it, but the benefits just aren't that visible in first-person shooters and the like. Shader Model 3.0 and Avivo are good things to have around as well; better API support, image quality, and video output are things that everyone wants.
However, the bottom line is that performance sells video cards. The first thing that people question when they are looking for a new card is just how well it runs in their favorite game. Hopefully, we will be able to shed some light on the issue here.
We will look at resolutions from 800x600 up to 2048x1536 and antialiasing tests will be included where possible. In games where we tested both with and without antialiasing, we will also show a graph of how performance drops due to AA scales with resolution. This data will be a lower-is-better graph (less drop in frame rate is a good thing) and will be shown scaled over resolution (as a performance drop will increase in percentage with resolution). The test system that we employed is the one used for our initial tests of the hardware.
With our recent architecture and feature set coverage over the ATI Radeon X1000 series launch, we were a little bit light on the performance numbers. Rather than fill out some of the tests and update the article, we decided to take a little more time and do it up right. We have heard the call for more game tests, and today, we bring them on in spades. Our expanded tests include the games mentioned in our earlier coverage, the much requested Battlefield 2, and we illustrate the stellar way in which the new X1000 series handles enabling 4xAA on the games that we tested.
While scaling-with-aa on the new X1000 series is very good, will it be good enough to make up for the price difference with competitive NVIDIA hardware? Certainly, the feature set is of value with ATI offering the added benefit of MSAA on MRT and floating point surfaces, high quality AF, SM3.0, and Avivo. But performance is absolutely critical on current and near term games. Currently, many HDR methods avoid floating point output and MRTs in order to maintain compatibility with AA on current hardware. Until game developers shift to full floating point framebuffers or make heavy use of multiple render targets, ATI's added AA support won't make much difference to gamers. High quality anisotropic filtering is definitely something that we have begged of NVIDIA and ATI for a long time and we are glad to see it, but the benefits just aren't that visible in first-person shooters and the like. Shader Model 3.0 and Avivo are good things to have around as well; better API support, image quality, and video output are things that everyone wants.
However, the bottom line is that performance sells video cards. The first thing that people question when they are looking for a new card is just how well it runs in their favorite game. Hopefully, we will be able to shed some light on the issue here.
We will look at resolutions from 800x600 up to 2048x1536 and antialiasing tests will be included where possible. In games where we tested both with and without antialiasing, we will also show a graph of how performance drops due to AA scales with resolution. This data will be a lower-is-better graph (less drop in frame rate is a good thing) and will be shown scaled over resolution (as a performance drop will increase in percentage with resolution). The test system that we employed is the one used for our initial tests of the hardware.
Facebook
Twitter
RSS
93 Comments
View All Comments
waldo - Friday, October 7, 2005 - link
I have been one that has been critical of the video card reviews, and am pleasantly suprised with this review! Thanks for the work Derek, and I am sure the overtime it took to punch this together...I can only imagine the hours you had to pull to put this together. That is why I love AnandTech! Great site, and responsive to the readers! Cheers!DerekWilson - Friday, October 7, 2005 - link
Anything we can do to help :-)I am glad that this article was satisfactory, and I regret that we were unable to provide this ammount of coverage in our initial article.
Keep letting us know what you want and we will keep doing our best to deliver.
Thanks,
Derek Wilson
supafly - Friday, October 7, 2005 - link
Maybe I missed it, but what system are these tests being done on?The tests from "ATI's Late Response to G70 - Radeon X1800, X1600 and X1300" were using:
ATI Radeon Express 200 based system
AMD Athlon 64 FX-55
1GB DDR400 2:2:2:8
120 GB Seagate 7200.7 HD
600 W OCZ PowerStreams PSU
Is this one the same? I would be interested to see the same tests run on a NF4 motherboard.
supafly - Friday, October 7, 2005 - link
Ahh, I skipped over that last part.. " The test system that we employed is the one used for our initial tests of the hardware."I would still like to see it on a NF4 mobo.
photoguy99 - Friday, October 7, 2005 - link
Vista will have DirectX 10, which adds geometry shaders and other bits.The ATI cards will run vista of course, but do everything DX10 hardware is capable of.
photoguy99 - Saturday, October 8, 2005 - link
Sorry, I meant the new ATI cards will *not* be DX10 compatible.The biggest difference is DX10 will introduce geometry shaders which is a whole new architectural concept.
This is a big difference that will make the X1800XT seem out of date.
The question is when will it seem out of date. Another year for Vista to be released with DX10, and then how long before a game not only has a DX10 rendering path, but has it do something interesting?
Hard to say - it could be the games with a DX10 rendering path show little difference, it could be you see a lot more geometry detail in UT2007.
Make your predications, spend your money, good luck.
Chadder007 - Friday, October 7, 2005 - link
Sooo...the new ATI's are pre-DX10 compliant? If so, what about the new Nvidia parts?DerekWilson - Friday, October 7, 2005 - link
This is not true -- DX10 will specific functions will not be compatible with either new ATI or NVIDIA hardware.Games written for Vista will be required to support DX9 initially and DX10 will be the advanced featureset. This will be to support hardware from the Radeon 9700 and GeFroce FX series through the Radeon X1K and 7800 series.
There is currently no hardware that is DX10 capable.
Xenoterranos - Saturday, October 8, 2005 - link
Im just hoping NVIDIA doesn't go braindead again ont he DX compliance. I'm still stuck with a non-fully compatible 5900 card. It runs HL2 very well even at high settings, but I know Im missing all the pretty DX9 stuff. I probably won't get another card untill DX10 hits, and then buy the first card that fully supports it.JarredWalton - Saturday, October 8, 2005 - link
Well, part of that is marketing. DX9 graphics are better than DX8.1, but it's not a massive difference on many games. Far Cry is almost entirely DX8.1, and other than a slight change to the water, you're missing nothing but performance.It's like the SM2.0 vs. SM3.0 debate. SM3.0 does allow for more complex coding, but mostly it just makes it so that the developers don't have to unroll loops. HDR, instancing, displacement mapping, etc. can all be done with SM2.0; it's just more difficult to accomplish and may not perform quite as fast.
Okay, I haven't ever coded SM2.0 or 3.0 (advanced graphics programming is beyond my skill level), but that's how I understand things to be. The SM3.0 brouhaha was courtesy of NVIDIA marketing, just like the full DX9 hubub was from ATI marketing. Anyway, MS and Intel have proven repeatedly that marketing is at least as important as technology.